Please use this identifier to cite or link to this item:
Title: Speaker clustering using dominant sets
Authors : Hibraj, Feliks
Vascon, Sebastiano
Stadelmann, Thilo
Pelillo, Marcello
Proceedings: Proceedings of the 24th International Conference on Pattern Recognition (ICPR 2018)
Pages : 1
Pages to: 6
Conference details: 24th International Conference on Pattern Recognition (ICPR 2018), Beijing, China, 20-28 August 2018
Publisher / Ed. Institution : IAPR
Publisher / Ed. Institution: Beijing
Issue Date: 2018
License (according to publishing contract) : Not specified
Type of review: Peer review (Publication)
Language : English
Subjects : Speaker recognition; Speaker embeddings
Subject (DDC) : 005: Computer programming, programs and data
410.285: Computational linguistics
Abstract: Speaker clustering is the task of forming speakerspecific groups based on a set of utterances. In this paper, we address this task by using Dominant Sets (DS). DS is a graphbased clustering algorithm with interesting properties that fits well to our problem and has never been applied before to speaker clustering. We report on a comprehensive set of experiments on the TIMIT dataset against standard clustering techniques and specific speaker clustering methods. Moreover, we compare performances under different features by using ones learned via deep neural network directly on TIMIT and other ones extracted from a pre-trained VGGVox net. To asses the stability, we perform a sensitivity analysis on the free parameters of our method, showing that performance is stable under parameter changes. The extensive experimentation carried out confirms the validity of the proposed method, reporting state-of-the-art results under three different standard metrics. We also report reference baseline results for speaker clustering on the entire TIMIT dataset for the first time.
Departement: School of Engineering
Organisational Unit: Institute of Applied Information Technology (InIT)
Publication type: Conference Paper
DOI : 10.21256/zhaw-4254
Appears in Collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
ICPR18b.pdf1.1 MBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.